The EDL-mPCIe-MA2485 PCIe mini-card from ADLINK features Intel® Movidius™ Myriad™ X VPU, providing an easy and flexible solution for computer vision and deep learning acceleration. Able to solve complex AI hardware design challenges, it enables integration of vision-based accelerators and inference engines to implement deep learning solutions at the edge.
The ADLINK EDL-mPCIe-MA2485 mPCIe module is available with single or dual onboard Intel® Movidius™ Myriad™ X VPUs with integrated LPDDR3 memory to meet all levels of performance requirements. The module is powered by the 3.3V mini PCIe connector from the host system with PCIe interface. It supports Intel’s OpenVINO™ toolkit which allows developers to leverage widely-used development standards.
EDL-mPCIe-MA2485 Specifications
- CPU
Single/Dual Intel® Movidius™ Myriad™ X MA2485 - Boot Image Device
USB - Form Factor
mPCIe ( PCIe mini-card ) - Interface
PCIe x1 - Memory
Integrated memory LPDDR3 4GB - Power
2 x PMIC (MAX77620) - PCIe Bridge
1x ASMedia* PCIe to USB3.0 (ASM1042A) - IO Expander
F75114 - RTC
1 x RTC connector - Status LED
1 x Green (3.3V) - Debug Port
2x 12-pin JTAG Connectors - Software Support
Intel® OpenVINO™ toolkit
Ordering Information
● EDL-mPCIe-MA2485
Dual Intel® Movidius™ Myriad™ X MA2485 embedded VPU module
Neural Compute Engine: Hardware Based Acceleration for Deep Neural Networks
Myriad™X features the new Neural Compute Engine - a purpose-built hardware acceleration unit designed to tremedously increase performance of deep neural networks without compromising the low power characteristics of the Myriad VPU product line.
Intel® Distribution of the OpenVINO™ toolkit
Intel® Distribution of OpenVINO™ toolkit is based on convolutional neural networks (CNN), the toolkit extends workloads across multiple types of Intel® platforms and maximizes performance. It can optimize pre-trained deep learning models such as Caffe, MXNET, and ONNX Tensorflow. The tool suite includes more than 20 pre-trained models, and supports 100+ public and custom models (includes Caffe*, MXNet, TensorFlow*, ONNX*, Kaldi*) for easier deployments across Intel® silicon products (CPU, GPU/Intel® Processor Graphics, FPGA, VPU).